
- Home
- Books
- Artificial Intelligence & Machine Learning
- Deep Learning & Neural Networks
- Math and Architectures of Deep Learning
Math and Architectures of Deep Learning by Krishnendu Chaudhury explains deep-learning architectures through the mathematics that makes them work. The book connects equations with implementation choices, developing the ideas needed to understand how neural networks learn. Worked explanations link model components with their computational roles, helping readers move beyond using a library interface to reasoning about the architecture and its training behavior.
What you will learn
- Connect linear algebra and calculus with neural networks
- Analyze the mathematics of model training
- Compare major deep-learning architectures
Who this is for
Developers and students seeking a mathematical account of deep learning. Basic programming, linear algebra and calculus are useful.


